Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to use softmax activation funciton for output layer #14

Open
yuanggeng opened this issue Mar 7, 2023 · 1 comment
Open

How to use softmax activation funciton for output layer #14

yuanggeng opened this issue Mar 7, 2023 · 1 comment

Comments

@yuanggeng
Copy link

I found you have all kinds of the activation funtions such as tanh, relu, and sigmoid. But there is no softmax function. So, we cannot verify the NN with the softmax activation function, right. Thank you.

@langkymus
Copy link
Collaborator

The technique works for any continuous (but not necessarily differentiable) activation function including softmax. Btw, we are no longer actively maintaining ReachNN*. Our latest tool for NNCS reachability analysis is POLAR: https://github.com/ChaoHuang2018/POLAR_Tool

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants